Kurtosis based pruning for a sensor-fusion system includes aligning candidate radar tracks with one of multiple candidate visual tracks. For each candidate vision track, a weight or other evidence of matching is assigned to each candidate radar track. An inverse of matching errors between each candidate vision track and each candidate radar track contributes to the evidence, which is normalized to produce, for each candidate vision track, a distribution associated with all candidate radar tracks. A Kurtosis or a shape of this distribution is calculated. Based on Kurtosis values, some candidate radar tracks are selected for matching and other remaining candidate radar tracks are pruned. The Kurtosis is used to determine how many candidates to retain and how many to prune.
Legal claims defining the scope of protection, as filed with the USPTO.
2. The method of claim 1, wherein determining whether the first object corresponding to the one of the vision tracks matches the second object corresponding to any of the non-vision tracks further includes refraining from matching the one of the vision tracks to the second object corresponding to the non-vision track of any other of the possible associations that are not selected for the high weight subset.
3. The method of claim 1, wherein the vision-sensor system comprises at least one camera and the set of vision tracks are derived from camera data of the one or more first objects.
4. The method of claim 1, wherein the non-vision-sensor system comprises one or more radar sensors, and the set of non-vision tracks are derived from radar data of the one or more second objects.
5. The method of claim 1, wherein the non-vision-sensor system comprises one or more lidar sensors, and the set of non-vision tracks are derived from lidar data of the one or more second objects.
6. The method of claim 1, wherein the non-vision-sensor system comprises one or more ultrasound sensors, and the set of non-vision tracks are derived from ultrasound data of the one or more second objects.
7. The method of claim 1, further comprising outputting, to a controller for use in controlling a vehicle, an indication of any of the set of vision tracks that are matched with any of the set of non-vision tracks.
8. The method of claim 7, further comprising refraining, from outputting to the controller, an indication of any of the set of vision tracks that are not matched with any of the set of non-vision tracks.
9. The method of claim 1, wherein at least one of the set of vision tracks and at least one of the set of non-vision tracks are associated with a portion of a stationary or moving object.
10. The method of claim 1, wherein the function applied to the likelihood of the false detection determined for each one of the possible associations comprises an inverse operation applied to the likelihood of a false detection for the one of the possible associations.
11. The method of claim 1, wherein the high weight subset comprises fewer than a total quantity of all other of the possible associations that are not selected for the high weight subset.
13. The system of claim 12, wherein the at least one processor is configured to determine whether the first object corresponding to the one of the vision tracks matches the second object corresponding to any of the set of non-vision tracks by refraining from matching the one of the vision tracks to the second object corresponding to the non-vision track of any other of the possible associations that are not selected for the high weight subset.
14. The system of claim 12, wherein the at least one processor is further configured to output, to a controller for use in controlling a vehicle, an indication of any of the set of vision tracks that are matched with any of the set of non-vision tracks.
15. The system of claim 14, further comprising refrain, from outputting to the controller, an indication of any of the set of vision tracks that are not matched with any of the set of non-vision tracks.
16. The system of claim 12, further comprising the vision-sensor system, wherein the vision-sensor system comprises at least one camera and the set of vision tracks are derived from camera data of the one or more first objects.
17. The system of claim 13, further comprising the non-vision-sensor system, wherein the non-vision-sensor system comprises one or more radar sensors, lidar sensors, and ultrasounds sensors.
18. The system of claim 17, wherein the set of non-vision tracks are derived from sensor data of the one or more second objects.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
February 22, 2023
August 6, 2024
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.